For Claude Code, Cursor, Codex, Windsurf and other MCP clients

One task list for you and your coding agents.

Add tasks from any browser, even your phone. Your agents read the same list over MCP, take the next task, leave notes, and close it with a summary. You see what each one is doing, what's finished, and which one needs you.

Start your 7-day trialSee how it works

$12/month after the trial. Card required. Cancel before day 7 and you pay nothing.

From sign-in to your agent's first task in three steps

  1. Sign in with your email

    We email you a sign-in link, so there's no password to create. Then start the 7-day trial with a card through Stripe.

  2. Paste a setup URL into your agent

    Make a setup URL in Settings. Paste it into Claude Code, Cursor, Codex or Windsurf and say "set this up". The agent adds the MCP server with a fresh API key and a short workflow for your CLAUDE.md.

  3. Work from the same list

    Add tasks in the web app. Your agent takes the top one, notes progress as it goes, and marks it done or blocked.

Your agent configures itself

A setup URL returns a short markdown file written for your agent. It holds a new API key, the MCP config for each client, and a CLAUDE.md snippet that tells the agent when to check the list. You never copy a key or edit a config file by hand.

A setup URL looks like this

https://taskhold.com/setup/a3f9c8e1d4b7.md

Each link carries its own API key and expires after 3 days. Revoke the key in Settings and the link stops working too.

Claude Code · Cursor · Codex · Windsurf

What it runs in Claude Code

claude mcp add --transport http --scope user taskhold \
  https://taskhold.com/api/mcp \
  --header "Authorization: Bearer atd_sk_..."

See what your agents did while you were away

The Agent Activity view shows the task each agent is on, the tasks that are blocked and waiting on you, recent agent notes, and the tasks agents created. Every change is stored with who made it.

What you write
Refactor the auth middleware so it doesn't depend on the user model. Check how session tokens are stored while you're in there.

Added by you

What your agent does
taskhold_get_current
  Nothing in progress
taskhold_list status:todo
  Refactor auth middleware (high)
taskhold_start
taskhold_add_note "Moved session lookup out of UserModel into AuthContext."
taskhold_create_from_todo src/auth/session.ts:88 "Session tokens stored unencrypted"
taskhold_complete "Middleware no longer imports UserModel. Tests pass."

Hand work to an agent and get it back with notes

Works with the agents you already use

Claude Code, Cursor, Codex, Windsurf, Cline and any other client that speaks the Model Context Protocol. Agents connect to one remote Streamable HTTP endpoint with their own API key.

Code TODOs become tasks

When an agent finds a TODO or a bug it isn't fixing right now, it files a task with the file path and line number, and you decide what happens next.

Blocked tasks come back to you

An agent that can't continue marks the task blocked and writes down why. You answer in the web app and unblock it.

Full change history

Every create, status change, note and edit is stored with whether a person or an agent made it, so you can trace any task back to its source.

Projects and labels

Group tasks by repo or client and filter by label. Agents can list both, so the tasks they create land in the right project.

One plan, priced per person

Pro includes every agent you run. It starts with a 7-day trial.

Pro

Monthly

$12/month

YearlyTwo months free

$120/year

  • Unlimited projects and tasks (fair use)
  • Every agent you run: Claude Code, Cursor, Codex, Windsurf and other MCP clients
  • Setup URLs that configure your agent for you
  • Agent Activity view and full change history
  • A separate API key per machine, revoke any time
  • Email support from the people who build it
Start your 7-day trial

7-day trial with a card up front. Cancel before it ends and you pay nothing. After that, cancel any time from Billing.

Questions

Which agents does it work with?

Claude Code, Cursor, Codex, Windsurf, Cline and any MCP client that can reach a remote Streamable HTTP server. Your setup URL includes the exact config for each of them.

Is my code sent anywhere?

No. Your agent sends only what it writes into a task: titles, notes, and any file paths or line numbers it chooses to include. We never see your repository, and we don't send your tasks to any AI model.

Where is my data stored?

In a SQLite database on our own server at DigitalOcean in the US. Stripe handles payments and holds your card details. Resend delivers sign-in emails. The privacy policy lists everything we keep.

What happens when the trial ends?

On day 7 your card is charged $12 for monthly or $120 for yearly, and the plan renews each period after that. Cancel before day 7 and you aren't charged.

How do I cancel?

Open Settings, then Billing, then Manage billing, and cancel in the Stripe portal. You keep access until the end of the period you paid for. Partial periods aren't refunded.

Can my team use it?

Each person subscribes and gets their own list. Shared team workspaces aren't built, so teammates can't see each other's tasks. If your team needs that, email hello@greatwork.company.

Can I export my data?

There's no export button yet. Email hello@greatwork.company from your account address and we'll send you your tasks, notes and history.

How are API keys kept safe?

We store a SHA-256 hash of each key, so the full key is shown only once. A setup URL keeps an encrypted copy of its key until the link expires. Use one key per machine and revoke any of them from Settings.

Give your agents a list to work from

Sign in with your email, start the trial, and paste a setup URL into your agent.

Start your 7-day trial

$12/month after the trial. Card required. Cancel before day 7 and you pay nothing.